Decentralized Robust Control of Coupled Multi-Agent Systems under Local Signal Temporal Logic Tasks

TL;DR

This paper presents a decentralized control framework for multi-agent systems where each agent has local temporal logic tasks, addressing task dependencies and conflicts through a hybrid control scheme with detection and repair mechanisms.

Contribution

It introduces a novel hybrid control approach that ensures local task satisfaction in multi-agent systems with interdependent temporal logic tasks, including an online detection and repair scheme.

Findings

Control law guarantees local task satisfaction under certain conditions

Hybrid detection and repair scheme resolves task conflicts online

Simulations demonstrate effectiveness of the proposed control framework

Abstract

Motivated by the recent interest in formal methods-based control of multi-agent systems, we adopt a bottom-up approach. Each agent is subject to a local signal temporal logic task that may depend on other agents behavior. These dependencies pose control challenges since some of the tasks may be opposed to each other. We first develop a local continuous feedback control law and identify conditions under which this control law guarantees satisfaction of the local tasks. If these conditions do not hold, we propose to use the developed control law in combination with an online detection & repair scheme, expressed as a local hybrid system. After detection of a critical event, a three-stage procedure is initiated to resolve the problem. The theoretical results are illustrated in simulations.